11170176

Artificial Intelligence Based Word Generation

PublishedNovember 9, 2021
Assigneenot available in USPTO data we have
Technical Abstract

Patent Claims
20 claims

Legal claims defining the scope of protection, as filed with the USPTO.

1

1. A computer-implemented method, comprising: identifying, by a data processing system, a theme for the poetic composition; building, by the data processing system, a datastore of text taxonomies that provide associative differences between two words in a plurality of words; analyzing, by the data processing system, the associative differences to determine a distance from a nexus for each of the plurality of words, wherein the nexus is determined according to the theme, and wherein the distance from the nexus to one of the plurality of words describes a suitability of the one of the plurality of words for use in the poetic composition for the theme; determining, by the data processing system, at least one associative word according to the distance from the nexus; and determining, by the data processing system, a rhyming word from the plurality of words according to the at least one associative word.

2

2. The method of claim 1 , wherein analyzing the associative differences to determine the distance from the nexus comprises analyzing the associative differences according to a star schema optimization.

3

3. The method of claim 1 , wherein identifying the theme comprises one of receiving input from a user and randomly determining the theme.

4

4. The method of claim 1 , wherein identifying the theme comprises determining the theme according to a history of past themes provided by the user.

5

5. The method of claim 1 , wherein determining at least one of the rhyming word and the associative word is determined according to Markov chains and transition matrices.

6

6. The method of claim 1 , further comprising: receiving, by the data processing system, a filter input from the user, wherein the determining the at least one associative word is determined according to the filter input.

7

7. The method of claim 1 , further comprising: receiving, by the data processing system, the filter input from the user, wherein the determining the rhyming word is determined according to the filter input.

8

8. The method of claim 1 , further comprising: receiving, by the data processing system, a word distance limitation, wherein the word distance limitation comprises a rule regarding the distance of the at least one associative word from the nexus, and wherein the determining the at least one associative word is determined according to the word distance limitation.

9

9. The method of claim 8 , wherein the word distance limitation comprises at least one of a maximum distance from the nexus and a minimum distance from the nexus.

10

10. A computer system comprising: a bus system; a storage device connected to the bus system, wherein the storage device stores program instructions; and a processor connected to the bus system, wherein the processor executes the program instructions to: identify a theme for the poetic composition; build a datastore of text taxonomies that provide associative differences between two words in a plurality of words; analyze the associative differences to determine a distance from a nexus for each of the plurality of words, wherein the nexus is determined according to the theme, and wherein the distance from the nexus to one of the plurality of words describes a suitability of the one of the plurality of words for use in the poetic composition for the theme; determine at least one associative word according to the distance from the nexus; and determine a rhyming word from the plurality of words according to the at least one associative word.

11

11. The computer system of claim 10 , wherein the program instructions to analyze the associative differences to determine the distance from the nexus comprises program instructions to analyze the associative differences according to a star schema optimization.

12

12. The computer system of claim 10 , wherein the processor further executes the program instructions to: receive a filter input from a user, wherein the program instructions to determine the at least one associative word comprises program instructions to determine the at least one associative word according to the filter input.

13

13. The computer system of claim 10 , wherein the processor further executes the program instructions to: receive the filter input from the user, wherein the program instructions to determine the rhyming word comprises program instructions to determine the rhyming word according to the filter input.

14

14. The computer system of claim 10 , wherein the processor further executes the program instructions to: receive a word distance limitation, wherein the word distance limitation comprises a rule regarding the distance of the at least one associative word from the nexus, and wherein the program instructions to determine the at least one associative word comprises program instructions to determine the at least one associative word according to the word distance limitation.

15

15. A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising: identifying a theme for the poetic composition; building a datastore of text taxonomies that provide associative differences between two words in a plurality of words; analyzing the associative differences to determine a distance from a nexus for each of the plurality of words, wherein the nexus is determined according to the theme, and wherein the distance from the nexus to one of the plurality of words describes a suitability of the one of the plurality of words for use in the poetic composition for the theme; determining at least one associative word according to the distance from the nexus; and determining a rhyming word from the plurality of words according to the at least one associative word.

16

16. The computer program product of claim 15 , wherein the analyzing the associative differences to determine the distance from the nexus comprises analyzing the associative differences according to a star schema optimization.

17

17. The computer program product of claim 15 , wherein the method further comprises: receiving a filter input from a user, wherein the determining the at least one associative word is determined according to the filter input.

18

18. The computer program product of claim 15 , wherein the method further comprises: receiving the filter input from the user, wherein the determining the rhyming word is determined according to the filter input.

19

19. The computer program product of claim 15 , wherein the method further comprises: receiving a word distance limitation, wherein the word distance limitation comprises a rule regarding the distance of the at least one associative word from the nexus, and wherein the determining the at least one associative word is determined according to the word distance limitation.

20

20. The computer program product of claim 19 , wherein the word distance limitation comprises at least one of a maximum distance from the nexus and a minimum distance from the nexus.

Patent Metadata

Filing Date

Unknown

Publication Date

November 9, 2021

Inventors

Jan B. Lillelund
Brian Rasmussen
Clea Anne Zolotow
Craig M. Trim

Want to explore more patents?

Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.

Citation & reuse

Analysis on this page is generated by Patentable — an AI-powered patent intelligence platform. AI-generated summaries, explanations, and analysis may be reused with attribution and a visible link back to the canonical URL below. Patent abstracts and claims are USPTO public domain.

Cite as: Patentable. “ARTIFICIAL INTELLIGENCE BASED WORD GENERATION” (11170176). https://patentable.app/patents/11170176

© 2026 Patentable. All rights reserved.

Patentable is a research and drafting-assistant tool, not a law firm, and does not provide legal advice. Documents we generate are drafts for review by a licensed patent attorney.